Retrieving Real-time Information to users in Public Transport Networks: An Application to the Lisbon Bus System

AbstractThis paper presents a real-time trip-planner system for the public transport in Lisbon. This system has the capability of informing potential customers about which are the best routes to make the trip they want, when they want and what are the expected travel times, based on the actual locations of the public transport vehicles and the travel speeds that can be estimated for the various relevant road segments for the next hour. Using four months of operation log-files from the bus operator Carris, a process of data mining was created to analyse and classify the information of travel times and speeds. The trip-planner is built upon an agent-based model that aims to simulate the transport network operation and create a model to make short-term travel times forecast. A system of dynamic queries was introduced in order to evaluate the built model. The obtained results indicate that this tool, if deployed, could achieve high accuracy levels in predictions and become very useful and valuable for urban public transport users